The output distance function is a key concept in economics. However, its empirical estimation is ... more The output distance function is a key concept in economics. However, its empirical estimation is less than satisfactory because it often violates properties dictated by economic theory. In this paper we introduce the neural distance function (NDF) which constitutes a global approximation to any arbitrary production technology with multiple outputs given by a neural network (NN) specification and imposes all
This repository contains the MATLAB functions relative to the paper 'Business models of the B... more This repository contains the MATLAB functions relative to the paper 'Business models of the Banks in the Euro Area', No. 2070, ECB Working Paper (https://www.ecb.europa.eu/pub/pdf/scpwps/ecb.wp2070.en.pdf?ee58f8028aa3d7b55dd977292218b268) by Matteo Farn\ue8 and Angelos Vouldis
We use a data‐driven classification of systemically important European banks into business models... more We use a data‐driven classification of systemically important European banks into business models based on confidential granular supervisory data and investigate whether banks following different models differ with respect to their capitalisation and profitability. Our aim is to locate the banks' business model in a risk‐return space. Using an instrumental variables approach, our econometric methodology addresses potential endogeneity issues. Overall, we find that wholesale funded and securities holding banks are positioned on a relatively high risk‐return trade‐off plane compared with commercial banks. On the other hand, traditional commercial banks earn lower returns with moderate risk.
This paper presents a methodology, called ROBOUT, to identify outliers conditional on a high-dime... more This paper presents a methodology, called ROBOUT, to identify outliers conditional on a high-dimensional noisy information set. In particular, ROBOUT is able to identify observations with outlying conditional mean or variance when the dataset contains leverage outliers, highly correlated variables, and a large dimension compared to the sample size. ROBOUT entails a preliminary robust imputation procedure, that prevents leverage outliers from corrupting predictor recovery, a selection stage of the statistically relevant predictors (through cross-validated LASSO-penalized Huber loss regression), the estimation of a robust regression model based on the selected predictors (via MM regression), and a criterion to identify conditional outliers. We conduct a comprehensive simulation study in which the proposed algorithm is tested under a wide range of perturbation scenarios. The combination formed by LASSO-penalized Huber loss and MM regression turns out to be the best in terms of conditio...
Contains data used in the paper "Measuring Credit Demand and Supply: A Bayesian Model with a... more Contains data used in the paper "Measuring Credit Demand and Supply: A Bayesian Model with an Application to Greece (2003–2011)" (published in the Jahrbücher für Nationalökonomie und Statistik)
The output distance function is a key concept in economics. However, its empirical estimation is ... more The output distance function is a key concept in economics. However, its empirical estimation is less than satisfactory because it often violates properties dictated by economic theory. In this paper we introduce the neural distance function (NDF) which constitutes a global approximation to any arbitrary production technology with multiple outputs given by a neural network (NN) specification and imposes all
This repository contains the MATLAB functions relative to the paper 'Business models of the B... more This repository contains the MATLAB functions relative to the paper 'Business models of the Banks in the Euro Area', No. 2070, ECB Working Paper (https://www.ecb.europa.eu/pub/pdf/scpwps/ecb.wp2070.en.pdf?ee58f8028aa3d7b55dd977292218b268) by Matteo Farn\ue8 and Angelos Vouldis
We use a data‐driven classification of systemically important European banks into business models... more We use a data‐driven classification of systemically important European banks into business models based on confidential granular supervisory data and investigate whether banks following different models differ with respect to their capitalisation and profitability. Our aim is to locate the banks' business model in a risk‐return space. Using an instrumental variables approach, our econometric methodology addresses potential endogeneity issues. Overall, we find that wholesale funded and securities holding banks are positioned on a relatively high risk‐return trade‐off plane compared with commercial banks. On the other hand, traditional commercial banks earn lower returns with moderate risk.
This paper presents a methodology, called ROBOUT, to identify outliers conditional on a high-dime... more This paper presents a methodology, called ROBOUT, to identify outliers conditional on a high-dimensional noisy information set. In particular, ROBOUT is able to identify observations with outlying conditional mean or variance when the dataset contains leverage outliers, highly correlated variables, and a large dimension compared to the sample size. ROBOUT entails a preliminary robust imputation procedure, that prevents leverage outliers from corrupting predictor recovery, a selection stage of the statistically relevant predictors (through cross-validated LASSO-penalized Huber loss regression), the estimation of a robust regression model based on the selected predictors (via MM regression), and a criterion to identify conditional outliers. We conduct a comprehensive simulation study in which the proposed algorithm is tested under a wide range of perturbation scenarios. The combination formed by LASSO-penalized Huber loss and MM regression turns out to be the best in terms of conditio...
Contains data used in the paper "Measuring Credit Demand and Supply: A Bayesian Model with a... more Contains data used in the paper "Measuring Credit Demand and Supply: A Bayesian Model with an Application to Greece (2003–2011)" (published in the Jahrbücher für Nationalökonomie und Statistik)
Uploads
Papers